june AMD Ryzen 9 3900XT 12-Core testing with a MSI MEG X570 GODLIKE (MS-7C34) v1.0 (1.B3 BIOS) and AMD Radeon RX 56/64 8GB on Ubuntu 22.04 via the Phoronix Test Suite. A: Processor: AMD Ryzen 9 3900XT 12-Core @ 3.80GHz (12 Cores / 24 Threads), Motherboard: MSI MEG X570 GODLIKE (MS-7C34) v1.0 (1.B3 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 500GB Seagate FireCuda 520 SSD ZP500GM30002, Graphics: AMD Radeon RX 56/64 8GB (1630/945MHz), Audio: AMD Vega 10 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek Device 2600 + Realtek Killer E3000 2.5GbE + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.04, Kernel: 5.15.0-22-generic (x86_64), Desktop: GNOME Shell 41.3, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 21.3.5 (LLVM 12.0.1), Vulkan: 1.2.195, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 B: Processor: AMD Ryzen 9 3900XT 12-Core @ 3.80GHz (12 Cores / 24 Threads), Motherboard: MSI MEG X570 GODLIKE (MS-7C34) v1.0 (1.B3 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 500GB Seagate FireCuda 520 SSD ZP500GM30002, Graphics: AMD Radeon RX 56/64 8GB (1630/945MHz), Audio: AMD Vega 10 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek Device 2600 + Realtek Killer E3000 2.5GbE + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.04, Kernel: 5.15.0-22-generic (x86_64), Desktop: GNOME Shell 41.3, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.42), Vulkan: 1.3.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 C: Processor: AMD Ryzen 9 3900XT 12-Core @ 3.80GHz (12 Cores / 24 Threads), Motherboard: MSI MEG X570 GODLIKE (MS-7C34) v1.0 (1.B3 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 500GB Seagate FireCuda 520 SSD ZP500GM30002, Graphics: AMD Radeon RX 56/64 8GB (1630/945MHz), Audio: AMD Vega 10 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek Device 2600 + Realtek Killer E3000 2.5GbE + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.04, Kernel: 5.15.0-22-generic (x86_64), Desktop: GNOME Shell 41.3, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.42), Vulkan: 1.3.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 D: Processor: AMD Ryzen 9 3900XT 12-Core @ 3.80GHz (12 Cores / 24 Threads), Motherboard: MSI MEG X570 GODLIKE (MS-7C34) v1.0 (1.B3 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 500GB Seagate FireCuda 520 SSD ZP500GM30002, Graphics: AMD Radeon RX 56/64 8GB (1630/945MHz), Audio: AMD Vega 10 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek Device 2600 + Realtek Killer E3000 2.5GbE + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.04, Kernel: 5.15.0-22-generic (x86_64), Desktop: GNOME Shell 41.3, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.42), Vulkan: 1.3.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 WebP2 Image Encode 20220422 Encode Settings: Quality 100, Lossless Compression Seconds < Lower Is Better A . 742.93 |=================================================================== B . 721.68 |================================================================= C . 722.89 |================================================================= D . 721.40 |================================================================= Java JMH Throughput Ops/s > Higher Is Better A . 23214280399.04 |======================================================== B . 24255951266.37 |=========================================================== C . 24266478961.70 |=========================================================== D . 24234601965.18 |=========================================================== WebP2 Image Encode 20220422 Encode Settings: Quality 95, Compression Effort 7 Seconds < Lower Is Better A . 323.97 |=================================================================== B . 309.66 |================================================================ C . 308.71 |================================================================ D . 310.50 |================================================================ Renaissance 0.14 Test: ALS Movie Lens ms < Lower Is Better A . 12757.9 |================================================================== B . 12616.7 |================================================================= C . 12677.3 |================================================================== D . 12638.5 |================================================================= Renaissance 0.14 Test: Akka Unbalanced Cobwebbed Tree ms < Lower Is Better A . 12754.4 |================================================================= B . 12943.4 |================================================================== C . 12759.6 |================================================================= D . 12947.6 |================================================================== SVT-HEVC 1.5.0 Tuning: 1 - Input: Bosphorus 4K Frames Per Second > Higher Is Better A . 2.82 |================================================================== B . 2.95 |===================================================================== C . 2.96 |===================================================================== D . 2.95 |===================================================================== GravityMark 1.53 Resolution: 1920 x 1080 - Renderer: OpenGL Frames Per Second > Higher Is Better A . 107.2 |==================================================================== B . 106.5 |==================================================================== C . 106.5 |==================================================================== D . 106.3 |=================================================================== GravityMark 1.53 Resolution: 1920 x 1080 - Renderer: Vulkan Frames Per Second > Higher Is Better A . 105.3 |==================================================================== B . 105.3 |==================================================================== C . 105.6 |==================================================================== D . 105.5 |==================================================================== GravityMark 1.53 Resolution: 2560 x 1440 - Renderer: OpenGL Frames Per Second > Higher Is Better A . 91.1 |===================================================================== B . 90.4 |==================================================================== C . 91.7 |===================================================================== D . 91.2 |===================================================================== GravityMark 1.53 Resolution: 3840 x 2160 - Renderer: OpenGL Frames Per Second > Higher Is Better A . 65.7 |===================================================================== B . 65.3 |===================================================================== C . 65.2 |==================================================================== D . 65.7 |===================================================================== GravityMark 1.53 Resolution: 2560 x 1440 - Renderer: Vulkan Frames Per Second > Higher Is Better A . 90.6 |===================================================================== B . 90.4 |===================================================================== C . 90.5 |===================================================================== D . 90.7 |===================================================================== GravityMark 1.53 Resolution: 3840 x 2160 - Renderer: Vulkan Frames Per Second > Higher Is Better A . 65.0 |===================================================================== B . 64.5 |==================================================================== C . 64.4 |==================================================================== D . 65.0 |===================================================================== GROMACS 2022.1 Implementation: MPI CPU - Input: water_GMX50_bare Ns Per Day > Higher Is Better A . 1.047 |============================================================== B . 1.138 |=================================================================== C . 1.140 |=================================================================== D . 1.155 |==================================================================== WebP2 Image Encode 20220422 Encode Settings: Quality 75, Compression Effort 7 Seconds < Lower Is Better A . 151.78 |=================================================================== B . 146.32 |================================================================= C . 148.84 |================================================================== D . 147.24 |================================================================= Renaissance 0.14 Test: Genetic Algorithm Using Jenetics + Futures ms < Lower Is Better A . 2666.5 |============================================================== B . 2888.2 |=================================================================== C . 2871.2 |================================================================== D . 2903.9 |=================================================================== libavif avifenc 0.10 Encoder Speed: 0 Seconds < Lower Is Better A . 134.16 |=================================================================== B . 129.53 |================================================================= C . 128.78 |================================================================ D . 128.40 |================================================================ oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 33601.70 |================================================================= B . 4101.51 |======== C . 4092.33 |======== D . 4110.74 |======== oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 35077.90 |================================================================= B . 4105.68 |======== C . 4117.24 |======== D . 4100.65 |======== InfluxDB 1.8.2 Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 val/sec > Higher Is Better A . 909621.0 |================================================================= B . 852735.1 |============================================================= C . 847482.0 |============================================================= D . 816036.0 |========================================================== ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better A . 60 |=============================================================== B . 68 |======================================================================= C . 68 |======================================================================= D . 68 |======================================================================= ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 59 |================================================ B . 78 |=============================================================== C . 60 |================================================ D . 88 |======================================================================= ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better A . 4580 |================================================================= B . 4858 |===================================================================== C . 4859 |===================================================================== D . 4795 |==================================================================== ONNX Runtime 1.11 Model: bertsquad-12 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better A . 432 |=================================================================== B . 449 |====================================================================== C . 449 |====================================================================== D . 451 |====================================================================== ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better A . 1117 |================================================================== B . 1165 |===================================================================== C . 1163 |===================================================================== D . 1165 |===================================================================== ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better A . 244 |================================================================== B . 256 |====================================================================== C . 257 |====================================================================== D . 257 |====================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 32226.30 |================================================================= B . 4089.48 |======== C . 4133.63 |======== D . 4126.65 |======== ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 1119 |=============================================== B . 1660 |===================================================================== C . 1183 |================================================= D . 1154 |================================================ ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 5775 |============================================================== B . 6058 |================================================================= C . 6445 |===================================================================== D . 5962 |================================================================ ONNX Runtime 1.11 Model: bertsquad-12 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 547 |=================================================================== B . 571 |====================================================================== C . 567 |====================================================================== D . 570 |====================================================================== ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 365 |======================================================== B . 323 |================================================== C . 337 |==================================================== D . 453 |====================================================================== ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better A . 4541 |================================================================== B . 4619 |=================================================================== C . 4586 |=================================================================== D . 4730 |===================================================================== ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 4435 |==================================================================== B . 4324 |================================================================== C . 4511 |===================================================================== D . 4423 |==================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 30995.10 |================================================================= B . 2496.51 |===== C . 2485.86 |===== D . 2495.97 |===== Renaissance 0.14 Test: Savina Reactors.IO ms < Lower Is Better A . 8321.1 |================================================================== B . 7969.9 |=============================================================== C . 7858.7 |============================================================== D . 8459.7 |=================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 28223.80 |================================================================= B . 2483.66 |====== C . 2492.88 |====== D . 2473.22 |====== oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 25968.50 |================================================================= B . 2485.34 |====== C . 2458.19 |====== D . 2458.93 |====== Renaissance 0.14 Test: Apache Spark PageRank ms < Lower Is Better A . 3174.2 |=================================================================== B . 3153.2 |=================================================================== C . 3116.0 |================================================================== D . 3117.0 |================================================================== Renaissance 0.14 Test: Apache Spark ALS ms < Lower Is Better A . 3211.3 |=================================================================== B . 3133.9 |================================================================= C . 3137.4 |================================================================= D . 3162.4 |================================================================== InfluxDB 1.8.2 Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 val/sec > Higher Is Better A . 1236274.6 |================================================================ B . 1240324.6 |================================================================ C . 1237035.8 |================================================================ D . 1195550.6 |============================================================== InfluxDB 1.8.2 Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 val/sec > Higher Is Better A . 1293571.6 |================================================================ B . 1291849.9 |================================================================ C . 1291195.0 |================================================================ D . 1240380.9 |============================================================= TensorFlow Lite 2022-05-18 Model: Inception V4 Microseconds < Lower Is Better A . 2445920.0 |================================================================ B . 42001.0 |= C . 42840.4 |= D . 42166.7 |= TensorFlow Lite 2022-05-18 Model: Inception ResNet V2 Microseconds < Lower Is Better A . 2330410.0 |================================================================ B . 42072.8 |= C . 42165.8 |= D . 41956.7 |= TensorFlow Lite 2022-05-18 Model: NASNet Mobile Microseconds < Lower Is Better A . 2271630.0 |================================================================ B . 15355.6 | C . 15359.5 | D . 15326.0 | Renaissance 0.14 Test: In-Memory Database Shootout ms < Lower Is Better A . 3614.9 |=============================================================== B . 3646.0 |================================================================ C . 3824.8 |=================================================================== D . 3732.7 |================================================================= Renaissance 0.14 Test: Apache Spark Bayes ms < Lower Is Better A . 2126.2 |================================================================== B . 2104.4 |================================================================== C . 2149.7 |=================================================================== D . 2113.8 |================================================================== simdjson 2.0 Throughput Test: PartialTweets GB/s > Higher Is Better A . 3.83 |================================================================== B . 3.99 |===================================================================== C . 4.00 |===================================================================== D . 4.00 |===================================================================== SVT-AV1 1.0 Encoder Mode: Preset 4 - Input: Bosphorus 4K Frames Per Second > Higher Is Better A . 2.467 |================================================================= B . 2.563 |==================================================================== C . 2.556 |==================================================================== D . 2.561 |==================================================================== libavif avifenc 0.10 Encoder Speed: 2 Seconds < Lower Is Better A . 66.03 |==================================================================== B . 62.50 |================================================================ C . 63.47 |================================================================= D . 62.15 |================================================================ simdjson 2.0 Throughput Test: DistinctUserID GB/s > Higher Is Better A . 4.59 |=================================================================== B . 4.72 |===================================================================== C . 4.55 |=================================================================== D . 4.72 |===================================================================== simdjson 2.0 Throughput Test: TopTweet GB/s > Higher Is Better A . 4.68 |===================================================================== B . 4.61 |==================================================================== C . 4.61 |==================================================================== D . 4.66 |===================================================================== TensorFlow Lite 2022-05-18 Model: SqueezeNet Microseconds < Lower Is Better A . 206917.00 |================================================================ B . 2898.87 |= C . 2894.31 |= D . 2888.78 |= TensorFlow Lite 2022-05-18 Model: Mobilenet Float Microseconds < Lower Is Better A . 240371.00 |================================================================ B . 2411.06 |= C . 2435.60 |= D . 2401.33 |= TensorFlow Lite 2022-05-18 Model: Mobilenet Quant Microseconds < Lower Is Better A . 44820.6 |================================================================== B . 3096.7 |===== C . 3146.6 |===== D . 3113.9 |===== Renaissance 0.14 Test: Scala Dotty ms < Lower Is Better A . 778.7 |=============================================================== B . 833.9 |==================================================================== C . 729.0 |=========================================================== D . 818.3 |=================================================================== Etcpak 1.0 Benchmark: Single-Threaded - Configuration: DXT1 Mpx/s > Higher Is Better A . 236.90 |================================================================ B . 237.86 |================================================================ C . 249.28 |=================================================================== D . 238.63 |================================================================ Etcpak 1.0 Benchmark: Single-Threaded - Configuration: ETC2 Mpx/s > Higher Is Better A . 232.17 |=============================================================== B . 246.14 |=================================================================== C . 246.81 |=================================================================== D . 247.11 |=================================================================== simdjson 2.0 Throughput Test: Kostya GB/s > Higher Is Better A . 2.93 |==================================================================== B . 2.92 |==================================================================== C . 2.89 |=================================================================== D . 2.98 |===================================================================== SVT-HEVC 1.5.0 Tuning: 1 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better A . 11.00 |================================================================ B . 11.63 |==================================================================== C . 11.63 |==================================================================== D . 11.61 |==================================================================== simdjson 2.0 Throughput Test: LargeRandom GB/s > Higher Is Better A . 1.01 |================================================================== B . 1.04 |==================================================================== C . 1.04 |==================================================================== D . 1.05 |===================================================================== Renaissance 0.14 Test: Finagle HTTP Requests ms < Lower Is Better A . 3814.1 |=================================================================== B . 3571.9 |=============================================================== C . 3529.2 |============================================================== D . 3587.1 |=============================================================== Renaissance 0.14 Test: Random Forest ms < Lower Is Better A . 743.4 |=================================================================== B . 721.2 |================================================================= C . 730.9 |================================================================== D . 751.7 |==================================================================== perf-bench Benchmark: Epoll Wait ops/sec > Higher Is Better A . 42469 |================================================================ B . 45429 |==================================================================== C . 45264 |==================================================================== D . 45400 |==================================================================== Stress-NG 0.14 Test: NUMA Bogo Ops/s > Higher Is Better A . 211.02 |=========================================== B . 328.20 |================================================================== C . 326.62 |================================================================== D . 331.54 |=================================================================== Stress-NG 0.14 Test: Malloc Bogo Ops/s > Higher Is Better A . 16082432.37 |=========================================================== B . 16996416.51 |============================================================== C . 16871709.82 |============================================================== D . 16827898.02 |============================================================= Stress-NG 0.14 Test: Atomic Bogo Ops/s > Higher Is Better A . 576128.96 |================================================================ B . 577614.81 |================================================================ C . 580078.48 |================================================================ D . 576825.66 |================================================================ Stress-NG 0.14 Test: Futex Bogo Ops/s > Higher Is Better A . 2786611.95 |========================================================== B . 2871422.77 |============================================================ C . 2787436.17 |========================================================== D . 3025044.82 |=============================================================== Stress-NG 0.14 Test: MMAP Bogo Ops/s > Higher Is Better A . 296.27 |================================================================== B . 300.58 |=================================================================== C . 300.57 |=================================================================== D . 298.14 |================================================================== Stress-NG 0.14 Test: IO_uring Bogo Ops/s > Higher Is Better A . 35619.31 |================================================================= B . 34951.82 |================================================================ C . 34815.95 |================================================================ D . 35188.01 |================================================================ Stress-NG 0.14 Test: Memory Copying Bogo Ops/s > Higher Is Better A . 4844.13 |=============================================================== B . 5038.57 |================================================================== C . 5039.59 |================================================================== D . 5048.06 |================================================================== Stress-NG 0.14 Test: MEMFD Bogo Ops/s > Higher Is Better A . 850.42 |================================================================= B . 871.88 |=================================================================== C . 869.61 |=================================================================== D . 867.30 |=================================================================== Stress-NG 0.14 Test: Glibc Qsort Data Sorting Bogo Ops/s > Higher Is Better A . 188.30 |================================================================ B . 196.50 |=================================================================== C . 197.10 |=================================================================== D . 195.83 |=================================================================== Stress-NG 0.14 Test: CPU Cache Bogo Ops/s > Higher Is Better A . 156.96 |================================================================== B . 152.09 |================================================================ C . 158.82 |=================================================================== D . 156.92 |================================================================== Stress-NG 0.14 Test: Matrix Math Bogo Ops/s > Higher Is Better A . 58365.05 |============================================================== B . 60985.00 |================================================================= C . 61156.12 |================================================================= D . 61125.26 |================================================================= Stress-NG 0.14 Test: System V Message Passing Bogo Ops/s > Higher Is Better A . 7796050.70 |============================================================= B . 8003229.07 |=============================================================== C . 7995516.42 |=============================================================== D . 7971710.38 |=============================================================== Stress-NG 0.14 Test: Glibc C String Functions Bogo Ops/s > Higher Is Better A . 1991624.53 |============================================================ B . 2026796.06 |============================================================= C . 2080090.43 |=============================================================== D . 2087104.71 |=============================================================== Stress-NG 0.14 Test: Context Switching Bogo Ops/s > Higher Is Better A . 4520622.35 |=========================================================== B . 4833096.84 |=============================================================== C . 4842631.56 |=============================================================== D . 4808874.54 |=============================================================== Stress-NG 0.14 Test: Socket Activity Bogo Ops/s > Higher Is Better A . 9558.26 |================================================================== B . 9191.93 |=============================================================== C . 9185.34 |=============================================================== D . 9193.24 |=============================================================== Stress-NG 0.14 Test: Vector Math Bogo Ops/s > Higher Is Better A . 86846.17 |============================================================== B . 90749.35 |================================================================= C . 90779.38 |================================================================= D . 90727.65 |================================================================= Stress-NG 0.14 Test: Semaphores Bogo Ops/s > Higher Is Better A . 2483545.87 |=============================================================== B . 2481083.26 |=============================================================== C . 2485080.45 |=============================================================== D . 2481553.24 |=============================================================== Stress-NG 0.14 Test: CPU Stress Bogo Ops/s > Higher Is Better A . 29249.94 |=============================================================== B . 30044.54 |================================================================= C . 29333.09 |=============================================================== D . 29002.22 |=============================================================== Stress-NG 0.14 Test: SENDFILE Bogo Ops/s > Higher Is Better A . 219949.89 |========================================================= B . 216302.59 |======================================================== C . 246261.31 |================================================================ D . 192604.94 |================================================== Stress-NG 0.14 Test: Forking Bogo Ops/s > Higher Is Better A . 52768.88 |============================================================== B . 54543.49 |================================================================= C . 54932.41 |================================================================= D . 54797.96 |================================================================= Stress-NG 0.14 Test: Crypto Bogo Ops/s > Higher Is Better A . 21561.58 |============================================================== B . 22488.17 |================================================================= C . 22493.23 |================================================================= D . 22466.90 |================================================================= perf-bench Benchmark: Futex Lock-Pi ops/sec > Higher Is Better A . 542 |========================================================= B . 669 |====================================================================== C . 663 |===================================================================== D . 649 |==================================================================== perf-bench Benchmark: Futex Hash ops/sec > Higher Is Better A . 4693851 |=============================================================== B . 4904887 |================================================================== C . 4910773 |================================================================== D . 4910651 |================================================================== SVT-AV1 1.0 Encoder Mode: Preset 4 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better A . 6.229 |================================================================== B . 6.440 |==================================================================== C . 6.435 |==================================================================== D . 6.428 |==================================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 92.13430 |================================================================= B . 5.65439 |==== C . 8.23900 |====== D . 7.65826 |===== oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 47.94820 |================================================================= B . 2.44129 |=== C . 2.44352 |=== D . 2.43000 |=== perf-bench Benchmark: Memcpy 1MB GB/sec > Higher Is Better A . 14.62 |============================================================= B . 16.24 |==================================================================== C . 14.77 |============================================================== D . 14.85 |============================================================== SVT-AV1 1.0 Encoder Mode: Preset 8 - Input: Bosphorus 4K Frames Per Second > Higher Is Better A . 30.78 |========================================================= B . 36.48 |==================================================================== C . 36.35 |==================================================================== D . 36.59 |==================================================================== x264 2022-02-22 Video Input: Bosphorus 4K Frames Per Second > Higher Is Better A . 35.58 |==================================================================== B . 35.64 |==================================================================== C . 35.36 |=================================================================== D . 34.85 |================================================================== oneDNN 2.6 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 73.17950 |================================================================= B . 4.70466 |==== C . 4.71020 |==== D . 4.70911 |==== oneDNN 2.6 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 59.13020 |================================================================= B . 1.80376 |== C . 1.79634 |== D . 1.81319 |== perf-bench Benchmark: Sched Pipe ops/sec > Higher Is Better A . 326839 |============================================================== B . 340408 |================================================================= C . 351971 |=================================================================== D . 344956 |================================================================== SVT-VP9 0.3 Tuning: VMAF Optimized - Input: Bosphorus 4K Frames Per Second > Higher Is Better A . 44.54 |=================================================================== B . 45.21 |==================================================================== C . 45.12 |==================================================================== D . 45.20 |==================================================================== SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4K Frames Per Second > Higher Is Better A . 43.96 |================================================================ B . 46.88 |==================================================================== C . 46.52 |=================================================================== D . 46.83 |==================================================================== SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 4K Frames Per Second > Higher Is Better A . 45.49 |============================================================== B . 49.51 |==================================================================== C . 49.84 |==================================================================== D . 49.86 |==================================================================== SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 4K Frames Per Second > Higher Is Better A . 42.20 |========================================================= B . 50.39 |==================================================================== C . 50.44 |==================================================================== D . 50.62 |==================================================================== oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 30.02690 |================================================================= B . 1.24528 |=== C . 1.16856 |=== D . 1.29107 |=== oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 36.17280 |================================================================= B . 1.85271 |=== C . 2.25790 |==== D . 1.99646 |==== libavif avifenc 0.10 Encoder Speed: 6, Lossless Seconds < Lower Is Better A . 11.43 |==================================================================== B . 10.88 |================================================================= C . 10.76 |================================================================ D . 10.98 |================================================================= oneDNN 2.6 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 73.36 |==================================================================== B . 11.98 |=========== C . 11.98 |=========== D . 11.38 |=========== oneDNN 2.6 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 36.708900 |================================================================ B . 0.933945 |== C . 0.930888 |== D . 0.924820 |== SVT-AV1 1.0 Encoder Mode: Preset 10 - Input: Bosphorus 4K Frames Per Second > Higher Is Better A . 72.34 |============================================================== B . 76.45 |================================================================= C . 78.41 |=================================================================== D . 79.79 |==================================================================== SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 4K Frames Per Second > Higher Is Better A . 75.56 |================================================================ B . 78.87 |=================================================================== C . 79.86 |==================================================================== D . 79.60 |==================================================================== libavif avifenc 0.10 Encoder Speed: 6 Seconds < Lower Is Better A . 8.089 |==================================================================== B . 7.654 |================================================================ C . 7.718 |================================================================= D . 7.619 |================================================================ perf-bench Benchmark: Memset 1MB GB/sec > Higher Is Better A . 69.02 |=============================================================== B . 72.01 |================================================================== C . 73.96 |==================================================================== D . 72.41 |=================================================================== SVT-AV1 1.0 Encoder Mode: Preset 12 - Input: Bosphorus 4K Frames Per Second > Higher Is Better A . 95.65 |================================================================= B . 98.21 |=================================================================== C . 98.22 |=================================================================== D . 99.57 |==================================================================== oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 41.19 |==================================================================== B . 24.91 |========================================= C . 24.96 |========================================= D . 24.85 |========================================= oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 36.96 |==================================================================== B . 22.59 |========================================== C . 22.59 |========================================== D . 22.50 |========================================= libavif avifenc 0.10 Encoder Speed: 10, Lossless Seconds < Lower Is Better A . 5.950 |==================================================================== B . 5.648 |================================================================= C . 5.601 |================================================================ D . 5.644 |================================================================= Etcpak 1.0 Benchmark: Multi-Threaded - Configuration: DXT1 Mpx/s > Higher Is Better A . 3072.05 |================================================================ B . 3156.58 |================================================================== C . 3169.25 |================================================================== D . 3162.38 |================================================================== Etcpak 1.0 Benchmark: Multi-Threaded - Configuration: ETC2 Mpx/s > Higher Is Better A . 3061.54 |================================================================ B . 3146.37 |================================================================== C . 3144.30 |================================================================== D . 3154.65 |================================================================== SVT-AV1 1.0 Encoder Mode: Preset 8 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better A . 116.76 |================================================================== B . 117.45 |================================================================== C . 117.33 |================================================================== D . 119.13 |=================================================================== perf-bench Benchmark: Syscall Basic ops/sec > Higher Is Better A . 17962305 |============================================================ B . 19410883 |================================================================= C . 17850063 |============================================================ D . 19384879 |================================================================= Nettle 3.8 Test: aes256 Mbyte/s > Higher Is Better A . 6059.02 |============================================================= B . 6131.07 |============================================================== C . 6541.11 |================================================================== D . 6515.50 |================================================================== WebP2 Image Encode 20220422 Encode Settings: Quality 100, Compression Effort 5 Seconds < Lower Is Better A . 4.242 |==================================================================== B . 4.110 |================================================================== C . 4.140 |================================================================== D . 4.140 |================================================================== x264 2022-02-22 Video Input: Bosphorus 1080p Frames Per Second > Higher Is Better A . 137.76 |================================================================= B . 141.25 |=================================================================== C . 140.99 |=================================================================== D . 141.00 |=================================================================== Glibc Benchmarks Benchmark: exp ns < Lower Is Better A . 16.19 |=================================================================== B . 16.44 |==================================================================== C . 16.15 |=================================================================== D . 16.38 |==================================================================== SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better A . 151.75 |================================================================ B . 159.49 |=================================================================== C . 158.60 |=================================================================== D . 158.69 |=================================================================== SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p Frames Per Second > Higher Is Better A . 168.00 |============================================================== B . 176.38 |================================================================== C . 176.32 |================================================================= D . 180.36 |=================================================================== SVT-VP9 0.3 Tuning: VMAF Optimized - Input: Bosphorus 1080p Frames Per Second > Higher Is Better A . 179.51 |================================================================= B . 184.60 |=================================================================== C . 183.53 |================================================================== D . 185.11 |=================================================================== SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p Frames Per Second > Higher Is Better A . 180.00 |================================================================ B . 187.87 |=================================================================== C . 187.19 |=================================================================== D . 187.34 |=================================================================== Glibc Benchmarks Benchmark: sin ns < Lower Is Better A . 65.33 |==================================================================== B . 62.17 |================================================================= C . 64.73 |=================================================================== D . 60.51 |=============================================================== WebP2 Image Encode 20220422 Encode Settings: Default Seconds < Lower Is Better A . 2.972 |=================================================================== B . 2.886 |================================================================= C . 3.003 |==================================================================== D . 2.896 |================================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 23.21980 |================================================================= B . 5.25702 |=============== C . 5.26468 |=============== D . 5.27803 |=============== oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 12.03100 |================================================================= B . 3.40615 |================== C . 3.38355 |================== D . 3.40609 |================== SVT-AV1 1.0 Encoder Mode: Preset 10 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better A . 223.22 |================================================================ B . 232.83 |=================================================================== C . 230.17 |================================================================== D . 226.79 |================================================================= SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better A . 274.85 |=============================================================== B . 290.42 |=================================================================== C . 287.22 |================================================================== D . 288.05 |================================================================== Glibc Benchmarks Benchmark: sincos ns < Lower Is Better A . 45.98 |==================================================================== B . 41.74 |============================================================== C . 41.74 |============================================================== D . 42.89 |=============================================================== SVT-AV1 1.0 Encoder Mode: Preset 12 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better A . 352.21 |=============================================================== B . 350.93 |=============================================================== C . 351.99 |=============================================================== D . 372.28 |=================================================================== Nettle 3.8 Test: sha512 Mbyte/s > Higher Is Better A . 637.04 |================================================================= B . 658.67 |=================================================================== C . 637.71 |================================================================= D . 637.39 |================================================================= Glibc Benchmarks Benchmark: cos ns < Lower Is Better A . 73.92 |==================================================================== B . 68.60 |=============================================================== C . 70.38 |================================================================= D . 68.63 |=============================================================== Glibc Benchmarks Benchmark: pthread_once ns < Lower Is Better A . 6.23097 |================================================================== B . 6.05998 |================================================================ C . 6.02658 |================================================================ D . 6.09718 |================================================================= Glibc Benchmarks Benchmark: tanh ns < Lower Is Better A . 38.37 |==================================================================== B . 35.61 |=============================================================== C . 38.06 |=================================================================== D . 38.33 |==================================================================== Glibc Benchmarks Benchmark: sinh ns < Lower Is Better A . 26.98 |==================================================================== B . 24.82 |=============================================================== C . 26.85 |==================================================================== D . 26.98 |==================================================================== Glibc Benchmarks Benchmark: atanh ns < Lower Is Better A . 38.34 |==================================================================== B . 37.46 |================================================================== C . 35.84 |================================================================ D . 35.87 |================================================================ Glibc Benchmarks Benchmark: asinh ns < Lower Is Better A . 30.64 |================================================================== B . 31.75 |==================================================================== C . 29.44 |=============================================================== D . 29.43 |=============================================================== Glibc Benchmarks Benchmark: ffs ns < Lower Is Better A . 6.09947 |================================================================== B . 5.68026 |============================================================= C . 6.08636 |================================================================== D . 5.69216 |============================================================== Glibc Benchmarks Benchmark: modf ns < Lower Is Better A . 7.09614 |================================================================== B . 6.53862 |============================================================= C . 6.71077 |============================================================== D . 6.54065 |============================================================= Glibc Benchmarks Benchmark: log2 ns < Lower Is Better A . 21.53 |==================================================================== B . 19.46 |============================================================= C . 20.73 |================================================================= D . 19.50 |============================================================== Glibc Benchmarks Benchmark: ffsll ns < Lower Is Better A . 7.04916 |================================================================== B . 6.46721 |============================================================= C . 6.93142 |================================================================= D . 6.46463 |============================================================= Glibc Benchmarks Benchmark: sqrt ns < Lower Is Better A . 7.86042 |================================================================== B . 7.27802 |============================================================= C . 7.46367 |=============================================================== D . 7.28112 |============================================================= Nettle 3.8 Test: chacha Mbyte/s > Higher Is Better A . 1068.17 |=========================================================== B . 1185.58 |================================================================== C . 1151.97 |================================================================ D . 1095.00 |============================================================= Nettle 3.8 Test: poly1305-aes Mbyte/s > Higher Is Better A . 3216.07 |================================================================== B . 3212.21 |================================================================== C . 3217.70 |================================================================== D . 3234.76 |================================================================== oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.6 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 2.6 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better Stress-NG 0.14 Test: x86_64 RdRand